Abstract | ||
---|---|---|
We propose a model of the joint variation of shape and appearance of portions of an image sequence. The model is conditionally linear, and can be thought of as an extension of active appearance models to exploit the temporal correlation of adjacent image frames. Inference of the model parameters can be performed efficiently using established numerical optimization techniques borrowed from finite-element analysis and system identification techniques. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/TPAMI.2006.243 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
numerical optimization technique,dynamic shape,active appearance model,finite-element analysis,joint variation,model parameter,system identification technique,temporal correlation,image sequence,appearance models,adjacent image frame,system identification,linear dynamical systems,active appearance models,finite element analysis,linear dynamical system,computational geometry | Active shape model,Computer vision,Linear dynamical system,Pattern recognition,Computer science,Linear model,Computational geometry,Image processing,Active appearance model,Image segmentation,Artificial intelligence,System identification | Journal |
Volume | Issue | ISSN |
28 | 12 | 0162-8828 |
Citations | PageRank | References |
18 | 0.88 | 18 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gianfranco Doretto | 1 | 1026 | 78.58 |
Stefano Soatto | 2 | 4967 | 350.34 |